How do I install the Operate Agent Memory skill?

Run npx skillmds@latest add hiteshbandhu/operate-agent-memory in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Operate Agent Memory safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Operate Agent Memory?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Operate Agent Memory free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Operate Agent Memory?

hiteshbandhu (@hiteshbandhu) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Operate Agent Memory by hiteshbandhu

Name: Operate Agent Memory
Author: hiteshbandhu

Operate Agent Memory

Runs checklists and workflows for agent context engineering — separating context from memory, smart truncation, sub-agent offload, and long-session evals. Use when the user hits context limits on observability or trace-heavy agents, designs multi-turn memory, or says "context management", "escape context window", "agent forgets follow-ups".

hiteshbandhu f1b9e1b 4 files · 6.2 KB Updated Sep 17, 2026

File contents

Operate agent memory

Action playbook from Sally-Ann Delucia (Arize Alex). Do not summarize the talk — pick a workflow and execute it.

Supporting files:

workflows.md — workflows A–E
source-index.md — talk → learnings

Optional deliverables: {SKILL_OUTPUT_DIR}/operate-agent-memory/

Step 0 — Pick workflow

What is the user trying to do?
├─ Diagnose context death spiral (retry adds data)     → A
├─ Design in-window vs memory split                    → B
├─ Implement truncation + retrievable store              → C
├─ Add long-session regression evals                     → D
└─ Split main vs sub-agent context budgets               → E

Stop summarizing once a workflow is identified — run its checklist.

Install

cp -r skills/operate-agent-memory ~/.claude/skills/
cp -r skills/operate-agent-memory ~/.cursor/skills/
cp -r skills/operate-agent-memory ~/.codex/skills/

Source: ingest-into-skills playlists/memory-ai-engineer/.

Cross-cutting rules

Rule	Source
Context = what the model sees; memory = what survives outside	[src-001 @ 7:48]
Agents fail on context, not prompts	[src-001 @ 14:14]
Naive head truncation breaks follow-ups	[src-001 @ 5:18]
Uncontrolled summarization is unreliable	[src-001 @ 6:15]
Long sessions fail late — eval turn N+1	[src-001 @ 8:44]

Output to user

Name the workflow (A–E) and deliverable
Save artifacts under ./skill-outputs/operate-agent-memory/ when useful
Do not auto-commit

Invocation examples

@operate-agent-memory our agent loses thread on turn 12
design sub-agents for heavy trace search
long-session eval harness for support copilot

---name: operate-agent-memorydescription: Runs checklists and workflows for agent context engineering — separating context from memory, smart truncation, sub-agent offload, and long-session evals. Use when the user hits context limits on observability or trace-heavy agents, designs multi-turn memory, or says "context management", "escape context window", "agent forgets follow-ups".---# Operate agent memoryAction playbook from Sally-Ann Delucia (Arize Alex). **Do not summarize the talk** — pick a workflow and execute it.**Supporting files:**- [workflows.md](workflows.md) — workflows A–E- [source-index.md](source-index.md) — talk → learningsOptional deliverables: `{SKILL_OUTPUT_DIR}/operate-agent-memory/`---## Step 0 — Pick workflow```What is the user trying to do?├─ Diagnose context death spiral (retry adds data) → A├─ Design in-window vs memory split → B├─ Implement truncation + retrievable store → C├─ Add long-session regression evals → D└─ Split main vs sub-agent context budgets → E```**Stop summarizing** once a workflow is identified — run its checklist.---## Install```bashcp -r skills/operate-agent-memory ~/.claude/skills/cp -r skills/operate-agent-memory ~/.cursor/skills/cp -r skills/operate-agent-memory ~/.codex/skills/```Source: [ingest-into-skills](https://github.com/hiteshbandhu/ingest-into-skills) `playlists/memory-ai-engineer/`.---## Cross-cutting rules| Rule | Source ||------|--------|| Context = what the model sees; memory = what survives outside | [src-001 @ 7:48] || Agents fail on context, not prompts | [src-001 @ 14:14] || Naive head truncation breaks follow-ups | [src-001 @ 5:18] || Uncontrolled summarization is unreliable | [src-001 @ 6:15] || Long sessions fail late — eval turn N+1 | [src-001 @ 8:44] |---## Output to user1. Name the workflow (A–E) and deliverable2. Save artifacts under `./skill-outputs/operate-agent-memory/` when useful3. Do not auto-commit---## Invocation examples```@operate-agent-memory our agent loses thread on turn 12design sub-agents for heavy trace searchlong-session eval harness for support copilot```

Frequently asked questions